Shared config, skills, and update scripts for Claude Code, Codex, and Gemini CLI
Skill Claude CodeCodex
Run a bounded autonomous planning loop before implementation: use scout workers to apply intuitive-reduce-entropy and grill-with-docs-batch, keep the main session as judge, iterate until the scope is clear, then present one recommended plan plus alternatives for a single user review. Follow the skill-runner Codex…
Skill Claude CodeCodex
Challenge an existing agent proposal through a small bounded set of independent review perspectives, then judge the findings into one simpler or more defensible recommendation. Use immediately after an agent proposes a solution when the user asks whether there is a simpler approach, wants a second opinion or other…
Skill Claude CodeCodex
Grouped grilling session that wraps grill-with-docs semantics while discussing related questions in batches, with explicit convergence checks so it stops when docs already contain enough decision quality. Use when the user wants to stress-test a plan against docs and domain language faster than one-question-at-a-time…
Skill Claude CodeCodex
Create and maintain an intuitive human documentation surface for AI-agent-developed repos. Use when humans should only need README.md, ARCHITECTURE.md, STATUS.md, and docs/human/ while planning logs, generated docs, retrospectives, ADR detail, and implementation evidence stay in AI-agent-only folders.
Skill Claude CodeCodex
Stable execution/change router after an approved plan, preflight contract, or tiny concrete task. Refactor-shaped work delegates to intuitive-refactor, and durable work runs through staged planning, review, GSD handoff, implementation, cleanup, and verification while keeping plan ledgers and active capsules compact by…
Skill Claude CodeCodex
Initialize, audit, aggressively slim, merge, and refresh project-local AGENTS.md and CLAUDE.md files from existing repo guidance, agent /init suggestions, stdin-bundled Codex init-style discovery, and intuitive workflow defaults. Use when setting up a repo for Claude Code/Codex, replacing symlinked agent files with…
Skill Claude CodeCodex
Port changes from one git worktree or checkout into the default repository folder's current branch, then by default sync the result to the remote default branch when everything is clean. Use when the user asks to move, copy, transfer, transplant, cherry-pick, apply a patch, or port worktree changes into the…
Skill Claude CodeCodex
Turn a vague task, plan, issue, or "LGTM/go ahead" request into an approval-ready preflight contract before implementation starts. Use when the user wants prompt preflight, clearer scope, non-goals, context package, acceptance criteria, definition of done, verification, stop gates, the exact execution command, or…
Skill Claude CodeCodex
Inspect a repository or plan and rank material simplification candidates. Use repo entropy mode when the cleanup owner is unknown, and plan entropy mode when an idea or plan needs blind spots found before approval. This skill discovers and routes work; it does not implement refactors.
Skill Claude CodeCodex
Refactor and cleanup router for known code/module/API seams, stale surfaces, compatibility shims, architecture cleanup targets, changed-code quality review, oversized modules, repeated cleanup campaigns, and recurring whole-repo architecture maintenance goals. Use this when the user names a concrete seam, wants…
Skill Claude CodeCodex
Shape a raw product or project idea into a bounded decision before planning or implementation. Use when deciding whether an idea deserves a bet, setting an appetite, comparing candidate bets under finite capacity, cutting scope, exposing rabbit holes and no-gos, or choosing BET, RESEARCH, RESHAPE, or PASS. This skill…
Skill Claude CodeCodex
Squash local GSD or agent-generated commit history into a clean, reviewable story while preserving important fixes. Use when the user asks to squash commits, clean git history, compress phase commits, prepare a branch before PR, compare aggressive vs moderate squash options, or preserve hotfix/security commits during…
Skill Claude CodeCodex
Use this skill whenever the user asks about unit test best practices, test organization, flat test suites, redundant tests, test refactors, pytest/JUnit/Jest/xUnit layout, test taxonomy, flaky tests, coverage quality, fixtures, mocks, parametrization, pruning existing UTs, or "which tests are worth keeping." It…
Skill Claude CodeCodex
Track goal-driven Multica issues. Use when a user creates or maintains Multica issues by pasting a /goal prompt, wants Codex to summarize that goal into a concise issue purpose, append a normalized goal-start comment, record completion evidence from real Multica execution run messages or a supplied session transcript…
Skill Claude CodeCodex
Run one approved implementation plan through multiple isolated candidate worktrees, then compare artifacts and rank the results. Use for best-of-N implementation or agent/model/harness bakeoffs against one shared baseline.
Skill Claude CodeCodex
Run evidence-led deep research using the host and repository's existing retrieval and delegation tools. Use when a question needs multiple sources, literature or ecosystem review, current technology comparison, competing claims reconciled, or a durable cited research report rather than a quick lookup. Do not use for…
Skill Claude CodeCodex
Run a bounded development task through named skills in an isolated, tmux-backed Codex or Claude session. Use for durable or artifact-sensitive worker phases, supervised skill runs, and post-run skill evaluation.